This guide provides step-by-step instructions for adding custom MCP (Model Context Protocol) servers to Conductor when the UI doesn't provide a built-in option.
jq command-line JSON processor installed
Think deeply about this infinite research task. You are about to orchestrate a sophisticated parallel multi-agent research system where each agent explores unique, non-overlapping angles of any topic.
Parse the following arguments from "$ARGUMENTS":
topic - The research topic to investigatenum_agents - Number of parallel research agents (3-10, default 5)max_iterations - Number of iterations (1-N or "infinite", default "infinite")
| process.env.ALACRITTY_LOG | |
| process.env.ALIYUN_REGION_ID | |
| process.env.ANTHROPIC_API_KEY | |
| process.env.ANTHROPIC_AUTH_TOKEN | |
| process.env.ANTHROPIC_BASE_URL | |
| process.env.ANTHROPIC_BETAS | |
| process.env.ANTHROPIC_CUSTOM_HEADERS | |
| process.env.ANTHROPIC_MODEL | |
| process.env.ANTHROPIC_SMALL_FAST_MODEL | |
| process.env.ANTHROPIC_SMALL_FAST_MODEL_AWS_REGION_AWS_REGION |
| { | |
| "messages": [ | |
| { | |
| "content": "Hello! I see you need help with interview analysis. Could you please provide more details about the interview or the specific task you want to accomplish? For example, are you looking to analyze interview transcripts, summarize key points, assess candidate responses, or something else? Let me know how I can assist you best!", | |
| "additional_kwargs": {}, | |
| "response_metadata": { | |
| "finish_reason": "stop", | |
| "model_name": "gpt-4.1-2025-04-14", | |
| "system_fingerprint": "fp_799e4ca3f1", | |
| "service_tier": "default" |
| { | |
| "data": { | |
| "analyzeVideoById": { | |
| "videoID": "250c4ef3-114a-4709-8fdc-3419d48f8908", | |
| "overallInterviewScore": 83, | |
| "questions": [ | |
| { | |
| "questionText": "So I have here this get active users with cat function. This function, it, it's taking, uh, a set of users. So each user, it's, it's represented by an object. Each object, um, has name, is active, and has cat as properties, right? So the idea is that we can return the correct set of users, uh, but with these two conditions: the users needs, needs to be active and also has a cat. Those two conditions. Okay?", | |
| "answerText": "Okay. Okay. All right. So (clears throat) this, uh, we're gonna use the filter, uh, method from the array. Uh, so we're gonna get a user and we're gonna filter only the ones that is active and user as cat. So I think this should do it.", | |
| "analysis": "The answer is clear and correct. The interviewee identifies the use of the filter method and specifies the two required conditions (acti |
| const ffmpeg = require('fluent-ffmpeg'); | |
| const path = require('path'); | |
| const m3u8Url = 'https://stream.mux.com/playback_id.m3u8'; | |
| const outputPath = path.join(__dirname, 'output.mp4'); | |
| ffmpeg(m3u8Url) | |
| .outputOptions([ | |
| '-c copy', |
| #!/bin/bash | |
| source ./send_email.sh | |
| # OAuth 2.0 configuration | |
| CLIENT_ID="" | |
| CLIENT_SECRET="" | |
| REDIRECT_URI="http://localhost:3000/api/xoauth/callback" | |
| AUTH_URL="https://login.xero.com/identity/connect/authorize" | |
| TOKEN_URL="https://identity.xero.com/connect/token" |
| # config/initializers/method_source_locator.rb | |
| # Utility to find the source location of a method based on its receiver and name | |
| def source_location(receiver, method_name) | |
| method_object = if receiver.singleton_class.method_defined?(method_name) || receiver.singleton_class.private_method_defined?(method_name) | |
| # Class method | |
| receiver.method(method_name) | |
| elsif receiver.method_defined?(method_name) || receiver.private_method_defined?(method_name) | |
| # Instance method | |
| receiver.instance_method(method_name) |
| const crypto = require("crypto"); | |
| const secretAccessKey = ""; // AWS_ACCESS_KEY_SECRET | |
| const regionName = "us-east-1"; | |
| // Assuming you've already set up your SES Policy on your IAM User: | |
| // { | |
| // "Version": "2012-10-17", | |
| // "Statement": [ | |
| // { |
| -- Generates multiple CREATE TABLE statements (without INDEXES) | |
| SELECT string_agg(create_table_stmt, E'\n\n' ORDER BY tablename) | |
| FROM ( | |
| SELECT | |
| tablename, | |
| 'CREATE TABLE ' || tablename || ' (' || column_defs || ');' as create_table_stmt | |
| FROM ( | |
| SELECT |